基於逐步光束法平差發展立體視覺里程計

本研究自製行動載台搭載經過率定的雙相機系統，拍攝立體像對，透過逐步光束法平差的演算法發展立體視覺里程計，其中利用攝影測量中的共面式以及共線式進行影像匹配後錯誤特徵點的除錯。為加強特徵點的穩定性，加入了循環匹配的概念，保留前一時刻像對與此時刻像對的四張影像共同的特徵點。最後利用逐步光束法平差，解算前後時刻拍攝的四張影像的相對位移量，將每一站解算成果結合即可恢復載台的移動軌跡。本實驗包含室內及室外場域，室內場地為成大測量系系館一樓，室外場地為成大博物館前的空地，成果顯示兩者的漂移比率分別小於1%及1.6%。

關鍵字

立體視覺里程計；共面式；共線式；逐步光束法平差；循環匹配

並列摘要

In this research, we develop the stereo visual odometry based on the algorithm of the stepwise bundle adjustment, with mobile stereo camera system which is made by ourselves. Coplanar condition and Collinear condition, which are the concepts of the Photogrammetry, are utilized to eliminate the error matches after image matching. To improve the feature points, the concept of circular matching is added into the algorithm, which means keeping the feature points that is caught by all adjacent image pairs. The last step is using the stepwise bundle adjustment to solve the relative motion of adjacent image pairs, and we can rebuild the whole trajectory of the mobile stereo system with combining all the results. There are indoor scenario and outdoor scenario in the experiment of this research. Indoor scenario is the ground floor of department of Geomatics of NCKU; outdoor scenario is the square in front of museum of NCKU. The results show that the drift ratio of the two scenario are smaller than 1% and 1.6% respectively.

並列關鍵字

Stereo Visual Odometry ； Coplanar Condition ； Collinear Condition ； Stepwise Bundle Adjustment ； Circular Matching

參考文獻

林照捷、曾義星，2019。以解算連續像對相對方位參數之單眼視覺里程計，航測及遙測學刊，24(2)：111-121，DOI：10.6574/JPRS.201906_24(2).0003。[Lin, C.C., and Tseng, Y.H., 2019. Model by using satellite images monocular visual odometry by solving relative orientation parameters of consecutive image pairs, Journal of Photogrammetry and Remote Sensing, 24(2): 111-121, DOI:10.6574/JPRS.201906_24(2).0003. (in Chinese)]

Fischler, M.A., and Bolles, R.C., 1981. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 24(6): 381-395, DOI: 10.1016/B978-0-08-051581-6.50070-2

Han, J.-Y., Guo, J., and Chou, J.-Y., 2010. A direct determination of the orientation parameters in the collinearity equations, IEEE Geoscience and Remote Sensing Letters, 8(2): 313-316, DOI: 10.1109/LGRS.2010.2066955

Liu, Y., Gu, Y., Li, J., and Zhang, X., 2017. Robust stereo visual odometry using improved RANSAC-based methods for mobile robot localization, Sensors, 17(10): 2339, DOI: 10.3390/s17102339

Nistér, D., Naroditsky, O., and Bergen, J., 2004. Visual odometry, in proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA, DOI: 10.1109/CVPR.2004.1315094

主題瀏覽